Saved in:
Bibliographic Details
Main Authors: Zhang, Xu, Wang, Qinghua, Zhao, Mengyang, Wang, Fang, Qu, Cunquan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.12688
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918295123263488
author Zhang, Xu
Wang, Qinghua
Zhao, Mengyang
Wang, Fang
Qu, Cunquan
author_facet Zhang, Xu
Wang, Qinghua
Zhao, Mengyang
Wang, Fang
Qu, Cunquan
contents Crime disrupts societal stability, making law essential for balance. In multidefendant cases, assigning responsibility is complex and challenges fairness, requiring precise role differentiation. However, judicial phrasing often obscures the roles of the defendants, hindering effective AI-driven analyses. To address this issue, we incorporate sentencing logic into a pretrained Transformer encoder framework to enhance the intelligent assistance in multidefendant cases while ensuring legal interpretability. Within this framework an oriented masking mechanism clarifies roles and a comparative data construction strategy improves the model's sensitivity to culpability distinctions between principals and accomplices. Predicted guilt labels are further incorporated into a regression model through broadcasting, consolidating crime descriptions and court views. Our proposed masked multistage inference (MMSI) framework, evaluated on the custom IMLJP dataset for intentional injury cases, achieves significant accuracy improvements, outperforming baselines in role-based culpability differentiation. This work offers a robust solution for enhancing intelligent judicial systems, with publicly code available.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12688
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Logic-Guided Multistage Inference for Explainable Multidefendant Judgment Prediction
Zhang, Xu
Wang, Qinghua
Zhao, Mengyang
Wang, Fang
Qu, Cunquan
Artificial Intelligence
Machine Learning
Crime disrupts societal stability, making law essential for balance. In multidefendant cases, assigning responsibility is complex and challenges fairness, requiring precise role differentiation. However, judicial phrasing often obscures the roles of the defendants, hindering effective AI-driven analyses. To address this issue, we incorporate sentencing logic into a pretrained Transformer encoder framework to enhance the intelligent assistance in multidefendant cases while ensuring legal interpretability. Within this framework an oriented masking mechanism clarifies roles and a comparative data construction strategy improves the model's sensitivity to culpability distinctions between principals and accomplices. Predicted guilt labels are further incorporated into a regression model through broadcasting, consolidating crime descriptions and court views. Our proposed masked multistage inference (MMSI) framework, evaluated on the custom IMLJP dataset for intentional injury cases, achieves significant accuracy improvements, outperforming baselines in role-based culpability differentiation. This work offers a robust solution for enhancing intelligent judicial systems, with publicly code available.
title Logic-Guided Multistage Inference for Explainable Multidefendant Judgment Prediction
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.12688